Paper: Bayesian Learning of Phrasal Tree-to-String Templates

ACL ID D09-1136
Title Bayesian Learning of Phrasal Tree-to-String Templates
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2009

We examine the problem of overcoming noisy word-level alignments when learn- ing tree-to-string translation rules. Our approach introduces new rules, and re- estimates rule probabilities using EM. The major obstacles to this approach are the very reasons that word-alignments are used for rule extraction: the huge space of possible rules, as well as controlling overfitting. By carefully controlling which portions of the original alignments are re- analyzed, and by using Bayesian infer- ence during re-analysis, we show signifi- cant improvement over the baseline rules extracted from word-level alignments.